© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15580
    Prev
    Next
    INDEX
    Explanations

    counting days and weeks

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is identify numeric quantity expressions (numbers and associated units of count or duration).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     they
    -1.52
    に行ってきました
    -1.37
    farer
    -1.23
     mereka
    -1.15
     first
    -1.15
     found
    -1.14
    oplasmic
    -1.13
     made
    -1.12
     too
    -1.11
    ysteine
    -1.11
    POSITIVE LOGITS
    without
    1.26
     integriert
    1.23
    Instead
    1.17
     berechtigt
    1.15
     mehrerer
    1.14
    lieving
    1.13
     gän
    1.13
     überweisen
    1.12
     süre
    1.11
     desselben
    1.11
    Activations Density 0.035%

    No Known Activations